A 7B Video Agent Beats a 72B Model by Looking Less

Featured

• Beyond the Current Observation: Evaluating Multimodal Large Language Models in Controllable Non-Markov Games score 10
  入选 HF Daily Papers; HF 热度: 43 upvotes (+4); 有代码实现; 关键词(1): fine-tuning
• Sumi: Open Uniform Diffusion Language Model from Scratch score 8
  入选 HF Daily Papers; HF 热度: 8 upvotes (+2); 有代码实现; 关键词(3): scaling, coding, reasoning
• Externalizing Research Synthesis and Validation in AI Scientists through a Research Harness score 7
  入选 HF Daily Papers; HF 热度: 2 upvotes (+1); 有代码实现; 关键词(1): reasoning
• Learning User Simulators with Turing Rewards score 6
  入选 HF Daily Papers; HF 热度: 2 upvotes (+1); 有代码实现

Also Worth Noting

• Robust and Interpretable Adaptation of Equivariant Materials Foundation Models via Sparsity-promoting Fine-tuning score 4
  关键词(2): fine-tuning, pre-training; 顶会接收: ICLR
• SCR-Guided Difficulty-Aware Optimization for Infrared Small Target Detection score 4
  关键词(1): lightweight; 顶会接收: CVPR
• Native Active Perception as Reasoning for Omni-Modal Understanding score 12
  入选 HF Daily Papers; HF 热度: 12 upvotes (+3); 有代码实现; 关键词(5): scaling, fine-tuning, agentic, reasoning, open-source; 顶会接收: ICML
• PEC-Home: Interpretation of Progressively Elliptical Commands in Smart Homes score 3
  顶会接收: ACL
• Physics-IQ Verified score 4
  入选 HF Daily Papers; HF 热度: 2 upvotes (+1)
• G-IdiomAlign: A Gloss-Pivoted Benchmark for Cross-Lingual Idiom Alignment score 3
  顶会接收: ACL